Nashville Entrepreneur Center · Internal edition

The EC Guide to Claude

Expert advice, field-tested prompts, and a sensible route to getting good — however far you want to go.

By Rob Williams · First edition · Updated July 7, 2026

Start here

Why this guide exists

On July 21, everyone at the EC gets a Claude account. That's the easy part. The hard part is the gap between having the tool and doing your job differently because of it — and most organizations never cross it.

The numbers are blunt. A December 2025 benchmark of 346 nonprofits found that nearly every organization uses AI now — and almost none report that it changed what they can accomplish. The difference isn't talent or budget. It's that only 4% ever document what works, so everyone experiments alone and the knowledge leaves when people do.

92%

of nonprofits now use AI tools in some capacity

7%

report major improvements in their ability to achieve their mission

81%

use AI ad hoc, without documented workflows — only 4% have them

Virtuous 2026 Nonprofit AI Adoption Report — 346 organizations surveyed, December 2025. Figures verified against the report.

This guide is the 4% move. It works like any good travel guide: opinionated, skimmable, and written by someone who's been there. The recipes are field-tested at the EC — several run in production right now. The itineraries pace your first 90 days. Nothing here is theory.

One standard governs everything: Claude is for doing your job better — not usage for its own sake. You stay the human in the loop. You own what you ship.

"The doing is the learning. No training document — including this one — substitutes for trying Claude on your actual work." From the EC team guide to working with AI
Expert tip

Anthropic's own rollout guide says it plainly: flipping the switch and sending an email isn't a rollout. It's a change of habit — and habits need curated first steps, not a blank page.

Anthropic — Deploying Claude across your organization →
If you only do one thing

Do the 20-minute setup. Claude without context is a stranger with a keyboard. Claude with context is a colleague. It changes every conversation that follows. Completely new to AI? Your one thing is even smaller: the starter pack.

Choose your route

How far are you going?

Three honest ways to travel. Pick the one that's true, not the one that sounds good — you can upgrade any time.

All three are legitimate. The guide is built so you can stop at any level and still be better off than yesterday.

Know before you go

Three rules. That's it.

The full AI Use Policy exists, and it's short. These three cover 95% of situations.

The rules of the road

The sharing rule

Before you paste, ask: would I be comfortable if this left the room? Founder names with their financials, donor data, applicant PII — swap in placeholders.

✕ "Jane Smith did $450,200 in 2024 revenue"
✓ "a founder with roughly $500K ARR"

The human rule

Every AI output goes through a human before it ships. You are accountable for what you send, post, or publish — whether or not Claude helped write it. AI drafts. You decide.

The three checks

Before anything AI-made is final: Fact check — did it invent a date or program detail? Tone check — does it sound like the EC or a robot? Security check — did a founder's name or number slip through?

Do EC work on the EC account. Our nonprofit plan doesn't train on EC data — free personal accounts may. Same Claude, different vault.
Expert tip

Wharton's Ethan Mollick finds the most advanced AI users are often already inside the organization — using it quietly, saying nothing, because old rules made it feel risky. These rules are permission-first on purpose: they're how we find our hidden experts, not how we police them.

Mollick on hidden adoption →
The essentials

The 20-minute setup

The packing list. Load it once and Claude stops sounding generic and starts sounding like the EC.

  1. Create a Project. In Claude: left sidebar → Projects → New Project. A Project is a workspace with memory — context loads once, not per conversation.
  2. Write your own instructions. Tell it your role, what you own, how you like to work. Like onboarding a new colleague. Ten minutes, plain language.
  3. Add the six blocks below to the Project's knowledge. Copy each, or download the whole kit as one file. Mission, history, strategy, programs, voice, guardrails — the packet you'd hand a new hire.
  4. Add 2–3 documents from your own desk. Templates, calendars, examples of work you're proud of. No founder or donor PII — see the rules of the road.
Local customs

How to talk to Claude

Five habits that separate people who get great output from people who get generic output. None require technical skill.

Talk to it like a colleague, not a search engine

Full sentences, real context, what the thing is for and who will read it. Keywords get you a search result. Background gets you a draft.

Show it what good looks like

Paste an example you're proud of — your best past newsletter, your favorite event copy — and say "like this." One example beats three paragraphs of description.

Ask for a shape

A table. A checklist. Three options with trade-offs. Two hundred words, not two thousand. If you don't name the shape, you get an essay.

Push back — twice

First drafts are a starting bid. Say what's wrong and why, then ask again. Mollick's framing: treat it like a brilliant friend with relevant expertise, not a vending machine. The quality of the output rises with the quality of the argument.

Make it ask you

End hard requests with "ask me what you need to know before answering." The questions it asks are often worth more than the first draft — they show you what you forgot to say.

Itineraries

Your first 90 days

Nobody's graded on speed. This is the route, not a race — check things off as you go. Your checkmarks save in this browser and nobody else sees them.

The best things to do

Our picks, by department

A good guide doesn't list every restaurant in town. Each department gets one pick — do that first — then the detours worth taking. Fill in the [brackets], keep what works.

Expert tip

Anthropic's cold-start warning: don't hand people a blank page. The teams that get value curate a first task per role — which is exactly what these picks are. Start with yours.

Anthropic — Scaling workflows across your organization →
The Lab

For those going deep

Wharton's Ethan Mollick says every organization needs a "Lab" — one or two people using AI daily — or it never learns what's actually possible. This section is the door.

The Lab isn't a job title and nobody gets assigned to it. It's self-selected: you use Claude daily, you try things that might not work, and you report back — including the failures. Mollick's model has three parts: leadership sets direction, the Lab experiments, and the crowd adopts what the Lab proves. Sam is doing the first part. The show-and-tell is the third. This is the middle.

Mastery has a ladder. Most of the team will live happily on rungs one and two. Lab members climb.

1

Chat

Where everyone starts: a very good colleague with amnesia. Every conversation begins from zero. Useful, and the ceiling is low.

2

Projects — the amnesia cure

Context loaded once, remembered always. This is the 20-minute setup, and it's where "generic AI" becomes "our AI." Most of the value for most people lives right here.

3

Skills and automations

Teach Claude a repeatable job — a documented workflow it runs the same way every time, triggered by an event or a single command instead of you remembering.

EC example: the 4-1-1 newsletter runs as a skill. One command, send-ready draft, real links.
4

Claude Code — the general agent

The top rung: Claude that works across files, data, and the web — and builds things. Dashboards, trainers, whole web pages. Power-user territory, and closer than it looks: Anthropic's Thariq Shihipar writes about using it as a general agent for everything, planning in HTML instead of walls of text.

EC examples: this guide, the NEXT Awards committee dashboard, the Find Your Program quiz, and Dakota's PM Trainer were all built here.
The deal

Lab membership costs one thing: you teach. What you learn goes into the Slack channel, this guide, and a show-and-tell slot. The Lab exists to feed the team — that's the whole model. If that's you, tell Rob. There's a Lab-track itinerary waiting in your first 90 days.

Ask a local

What does your week look like?

The best use cases aren't the flashy ones — they're the tasks you do so often you stopped noticing them. Tap anything that sounds familiar.

The guide recommends

The concierge desk. Your repeat task isn't listed? That's the most valuable thing you can tell us. Post "I keep doing ___ every week" in the Claude Slack channel — or bring the project to a build session and Rob will build it with you, live. That's the highest-value hour in this guide, and it's how new picks get added.
Expert tip

Where new recipes come from: Claire Vo's How I AI is a library of real, specific ways people use AI in their actual work. When the concierge desk runs dry, that's the hunting ground.

How I AI (example episode) →
Locals' favorites

Built at the EC, with Claude

Real work by real teammates — not demos. The reserved lines are waiting for your name.

To get listed: do a thing with Claude, post it in the Slack channel — the prompt, what it made, what it saved — and it goes in the next edition. Honest experiments beat polished case studies. Failures count double; they teach more.

Practical matters

Questions people actually ask

Is this page tracking my usage?
No. It's a static page — no logins, no analytics, nothing reported to anyone. Itinerary checkmarks and your route choice save in your own browser and only you can see them.
Do I have to use Claude?
No. Everyone gets an account; nobody's forced to use it. The standard is your job done better — if a tool doesn't help your work, don't use it. NTEN's Amy Sample Ward puts the healthy skepticism well: question the hype, and adopt tools that serve the people at the center of the work — never tools that add risk to them. Her conversation with Bridgespan is worth ten minutes. That said: try Claude on one real task before deciding.
What if Claude gets something wrong?
It will, occasionally, with confidence. That's why the three checks exist and why every output goes through a human. You own what you ship — Claude is the draft, you're the editor.
Can I put founder or donor information in?
Names plus financials, no. Swap in placeholders — "a founder with roughly $500K ARR" works as well as the real name for almost every task. See the rules of the road.
What's the Lab?
The one or two people who use Claude daily, try the ambitious stuff, and teach the rest of us what works. Self-selected, open door, comes with homework. Details here.
Everyone keeps using words I don't know.
Nobody was born knowing them. The phrasebook translates every term this guide uses into plain English — markdown, tokens, agents, all of it. If a word you hit isn't there, ask in Slack and it gets added.
How does something get added to this guide?
Post it in the Claude Slack channel. Rob curates new picks and favorites into the next edition, and the best ones get featured at show-and-tell.
Who wrote this?
Rob, with Claude — which is rather the point. Every recipe here has been run on real EC work, and every stat was verified against its primary source.
The phrasebook

Words you'll hear

Every trade has its jargon; nobody was born knowing this one. Plain-English translations, no jargon shame. Missing a word? Ask in Slack and it gets added.

Everyday words

AI · LLM

"Large language model" — software that read an enormous amount of text and got very good at predicting what comes next. Claude is one. Not magic, not a person: a very well-read collaborator that still needs your judgment.

Claude

The AI assistant we use, made by Anthropic. Lives at claude.ai, as a desktop and phone app, and in power tools like Claude Code.

Prompt

Whatever you type to Claude — a question, an instruction, a pile of messy notes. There is no wrong format and no secret handshake.

Conversation · thread · chat

One back-and-forth session. Claude remembers everything inside a conversation, and nothing across them — unless you use a Project.

Context

The background you give Claude: who you are, what the work is for, what good looks like. More context, better output. The whole Essentials section is context.

Project

A Claude workspace with memory — your instructions plus files it keeps across every conversation. The amnesia cure from the 20-minute setup.

Markdown · .md

A plain-text format that uses simple symbols: # for a heading, - for a list, **bold**. AI tools love it because it's just text with structure. If you can read this sentence, you can read markdown. The starter kit downloads as a .md file — open it in any text editor, or paste it straight into Claude.

Hallucination

When AI states something false, confidently. It happens. It's why the fact check exists — and why you're the editor.

Words from further up the ladder

Context window

How much one conversation can hold before the earliest parts start to fade. Why a very long thread eventually gets forgetful — and why fresh threads per project work better.

Artifact

A document, web page, or mini-app Claude builds beside the chat, shareable by link. Dakota's PM Trainer is one.

Human in the loop

Our standing rule: a person reviews every AI output before it ships. That person is you.

Skill · automation

A repeatable job Claude has been taught to run the same way every time — like the 4-1-1 draft. One command instead of re-explaining from scratch.

Agent

AI that acts on a trigger — "when this happens, do that" — instead of waiting for you to ask. Rung four of the ladder.

Claude Code

Anthropic's power tool: Claude that works across files, data, and the web — and builds things. This guide came out of it.

Token

The chunks AI actually reads and writes — roughly three-quarters of a word each. Only matters when you hit a usage limit; now you know what the limit is counting.

MCP · connector

The plumbing that lets Claude reach other tools — Slack, Drive, calendars — with your permission. It's how agents get hands.

Want the official tour of the screen itself? Anthropic's Get started with Claude is five minutes well spent.

The reading room

The whole shelf

You don't need any of this to start. For the few who finish the guide and want to go to the source.

The spine — Anthropic's rollout thinking

Anthropic's playbook: champions → pilot → scale. Our rollout matches it — sized down from enterprise to thirteen people.

The "launch ≠ enablement" argument, and why curated first tasks beat blank pages.

Product news and best practices, straight from the source. Where new capabilities show up first.

The frameworks — Ethan Mollick

The book behind our human-in-the-loop rules. Use AI for everything you ethically can; keep human judgment on the output. Rob has a copy you can borrow.

The three-part model our rollout borrows. Leadership sets direction, the Lab experiments, the crowd adopts.

Why your best AI users are already here, quietly — and why permission-first policy surfaces them.

Sized for nonprofits

The benchmark behind this guide's numbers: 346 nonprofits on why most stall and what the 7% do differently.

Free policy template and readiness checklist. Our three rules are the cut-down version of this thinking.

The sector case, plus NTEN's Amy Sample Ward as the honest counterweight to the hype.

For the Lab — practitioner technique

Real, specific workflows from real practitioners. The hunting ground for our next recipe.

Claude Code as a general agent; planning in HTML instead of text walls. Rung-four territory.

Product and AI tactics. Pull when curious — idea source, not required reading.